© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16922
    Prev
    Next
    INDEX
    Explanations

    goal or objective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     almost
    -0.10
     quite
    -0.10
    abra
    -0.10
     surely
    -0.10
     truly
    -0.10
     insist
    -0.09
     DOUBLE
    -0.09
    uju
    -0.09
    _hint
    -0.09
     nearly
    -0.08
    POSITIVE LOGITS
     ASAP
    0.19
     möglich
    0.16
     maximize
    0.15
     maxim
    0.15
     preferably
    0.14
     efficiently
    0.13
     maximizing
    0.13
     entertaining
    0.12
     safely
    0.12
     whichever
    0.12
    Activations Density 0.499%

    No Known Activations